Getting Started

Dyfan Jones

The noctua package aims to make it easier to work with data stored in AWS Athena. noctua package attempts to provide three levels of interacting with AWS Athena:

• Low - level API: This provides more finer tuning of AWS Athena backend utilising the AWS SDK paws. This includes configuring AWS Athena Work Groups to assuming different roles within AWS when connecting to AWS Athena.
• DBI interface: This is the primary goal of noctua, by providing a DBI interface to AWS Athena. Users are able to interact with AWS Athena utilising familiar functions and methods they have used for other Databases from R.
• dplyr interface: As dplyr is coming more popular, noctua aims to give dplyr a seamless interface into AWS Athena.

# cran version
install.packages("noctua")

# Dev version
remotes::install_github("dyfanjones/noctua")

library(DBI)
library(noctua)

con <- dbConnect(athena())

# list all current work groups in AWS Athena
list_work_groups(con)

# Create a new work group
create_work_group(con, "demo_work_group", description = "This is a demo work group",
                  tags = tag_options(key= "demo_work_group", value = "demo_01"))

library(DBI)

con <- dbConnect(noctua::athena())

# Get metadata 
dbGetInfo(con)

# $profile_name
# [1] "default"
# 
# $s3_staging
# [1] ######## NOTE: Please don't share your S3 bucket to the public
# 
# $dbms.name
# [1] "default"
# 
# $work_group
# [1] "primary"
# 
# $poll_interval
# NULL
# 
# $encryption_option
# NULL
# 
# $kms_key
# NULL
# 
# $expiration
# NULL
# 
# $region_name
# [1] "eu-west-1"
# 
# $paws
# [1] "0.1.6"
# 
# $noctua
# [1] "1.5.1"

# create table to AWS Athena
dbWriteTable(con, "iris", iris)

dbGetQuery(con, "select * from iris limit 10")
# Info: (Data scanned: 860 Bytes)
#  sepal_length sepal_width petal_length petal_width species
# 1:           5.1         3.5          1.4         0.2  setosa
# 2:           4.9         3.0          1.4         0.2  setosa
# 3:           4.7         3.2          1.3         0.2  setosa
# 4:           4.6         3.1          1.5         0.2  setosa
# 5:           5.0         3.6          1.4         0.2  setosa
# 6:           5.4         3.9          1.7         0.4  setosa
# 7:           4.6         3.4          1.4         0.3  setosa
# 8:           5.0         3.4          1.5         0.2  setosa
# 9:           4.4         2.9          1.4         0.2  setosa
# 10:          4.9         3.1          1.5         0.1  setosa

library(dplyr)

athena_iris <- tbl(con, "iris")

athena_iris %>%
  select(species, sepal_length, sepal_width) %>% 
  head(10) %>%
  collect()

# Info: (Data scanned: 860 Bytes)
# # A tibble: 10 x 3
# species  sepal_length sepal_width
# <chr>           <dbl>       <dbl>
# 1 setosa            5.1         3.5
# 2 setosa            4.9         3  
# 3 setosa            4.7         3.2
# 4 setosa            4.6         3.1
# 5 setosa            5           3.6
# 6 setosa            5.4         3.9
# 7 setosa            4.6         3.4
# 8 setosa            5           3.4
# 9 setosa            4.4         2.9
# 10 setosa           4.9         3.1